© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8838
    Prev
    Next
    INDEX
    Explanations

    Ball

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    M
    -0.31
    iliation
    -0.28
    ì§Ģê³ł
    -0.27
    ifact
    -0.27
    æ´»è·ĥ
    -0.25
    ments
    -0.25
    æĸŃ
    -0.24
    年以æĿ¥
    -0.24
    cing
    -0.24
    lia
    -0.24
    POSITIVE LOGITS
    entine
    0.29
    ä¹ĺ
    0.28
    .intellij
    0.28
     addAction
    0.28
    侯
    0.27
     bearings
    0.27
    ä»ĵ
    0.26
    ä¹IJåĽ¢
    0.26
    __('
    0.25
    unnable
    0.25
    Activations Density 0.005%

    No Known Activations